python - 如何在 scikit-learn 中使用数字索引与 pd.DataFrame 进行交叉验证（禁用 _safe_split）？

Question

我想禁用safe_indexing并强制我给我的模型的指标。

我不能简单地这样做X.values，y.values因为我有一个自定义分类器，我已经在其中使用了列/属性标签__init__（对算法至关重要）。

这来自以下代码行：

model_selection.cross_val_score(model, X=X, y=y, cv=cv, n_jobs=1, scoring="accuracy")

wherecv是具有数字索引的列表列表

X必须是一个pd.DataFrame并且cv必须是预定义的索引。我怎样才能使这项工作？

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-74-e1775ca32abb> in <module>()
      1 smc.fit(X,y)
----> 2 smc.cross_validate(X,y,cv=cv, n_jobs=1)

<ipython-input-72-61f814fd075c> in cross_validate(self, X, y, cv, scoring, n_jobs, **args)
    150                     cv_idx.append((idx_tr.map(lambda x:X.index.get_loc(x)), idx_te.map(lambda x:X.index.get_loc(x))))
    151                 cv = cv_idx
--> 152         return model_selection.cross_val_score(self, X=X, y=y, cv=cv, n_jobs=n_jobs, scoring=scoring, **args)

~/anaconda/envs/python3/lib/python3.6/site-packages/sklearn/model_selection/_validation.py in cross_val_score(estimator, X, y, groups, scoring, cv, n_jobs, verbose, fit_params, pre_dispatch)
    340                                 n_jobs=n_jobs, verbose=verbose,
    341                                 fit_params=fit_params,
--> 342                                 pre_dispatch=pre_dispatch)
    343     return cv_results['test_score']
    344 

~/anaconda/envs/python3/lib/python3.6/site-packages/sklearn/model_selection/_validation.py in cross_validate(estimator, X, y, groups, scoring, cv, n_jobs, verbose, fit_params, pre_dispatch, return_train_score)
    204             fit_params, return_train_score=return_train_score,
    205             return_times=True)
--> 206         for train, test in cv.split(X, y, groups))
    207 
    208     if return_train_score:

~/anaconda/envs/python3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in __call__(self, iterable)
    777             # was dispatched. In particular this covers the edge
    778             # case of Parallel used with an exhausted iterator.
--> 779             while self.dispatch_one_batch(iterator):
    780                 self._iterating = True
    781             else:

~/anaconda/envs/python3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in dispatch_one_batch(self, iterator)
    623                 return False
    624             else:
--> 625                 self._dispatch(tasks)
    626                 return True
    627 

~/anaconda/envs/python3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in _dispatch(self, batch)
    586         dispatch_timestamp = time.time()
    587         cb = BatchCompletionCallBack(dispatch_timestamp, len(batch), self)
--> 588         job = self._backend.apply_async(batch, callback=cb)
    589         self._jobs.append(job)
    590 

~/anaconda/envs/python3/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py in apply_async(self, func, callback)
    109     def apply_async(self, func, callback=None):
    110         """Schedule a func to be run"""
--> 111         result = ImmediateResult(func)
    112         if callback:
    113             callback(result)

~/anaconda/envs/python3/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py in __init__(self, batch)
    330         # Don't delay the application, to avoid keeping the input
    331         # arguments in memory
--> 332         self.results = batch()
    333 
    334     def get(self):

~/anaconda/envs/python3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in __call__(self)
    129 
    130     def __call__(self):
--> 131         return [func(*args, **kwargs) for func, args, kwargs in self.items]
    132 
    133     def __len__(self):

~/anaconda/envs/python3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in <listcomp>(.0)
    129 
    130     def __call__(self):
--> 131         return [func(*args, **kwargs) for func, args, kwargs in self.items]
    132 
    133     def __len__(self):

~/anaconda/envs/python3/lib/python3.6/site-packages/sklearn/model_selection/_validation.py in _fit_and_score(estimator, X, y, scorer, train, test, verbose, parameters, fit_params, return_train_score, return_parameters, return_n_test_samples, return_times, error_score)
    446     start_time = time.time()
    447 
--> 448     X_train, y_train = _safe_split(estimator, X, y, train)
    449     X_test, y_test = _safe_split(estimator, X, y, test, train)
    450 

~/anaconda/envs/python3/lib/python3.6/site-packages/sklearn/utils/metaestimators.py in _safe_split(estimator, X, y, indices, train_indices)
    198             X_subset = X[np.ix_(indices, train_indices)]
    199     else:
--> 200         X_subset = safe_indexing(X, indices)
    201 
    202     if y is not None:

~/anaconda/envs/python3/lib/python3.6/site-packages/sklearn/utils/__init__.py in safe_indexing(X, indices)
    144     if hasattr(X, "iloc"):
    145         # Work-around for indexing with read-only indices in pandas
--> 146         indices = indices if indices.flags.writeable else indices.copy()
    147         # Pandas Dataframes and Series
    148         try:

AttributeError: 'list' object has no attribute 'flags'

针对评论中的建议（2018-6-04）：

标签： pythonpandasindexingscikit-learncross-validation